The segmentation of a complex scene, such as a sample of muscle fibre types, is notoriously diflcult and in most published studies on quantitative muscle fibre analysis it was performed manually. We propose a semi-automatic segmentation method which gives good results, similar to those obtained by manual segmentation, but signi3cantly reauces the time necessary for user interaction. Instead of manually tracing each jibre boundary we build a Voronoi diagram based on the set of points which represent the muscle fibre centroids. The edge of each Voronoi polygon is used as the initial position of a snake which is reshaped by an energy minimization process. The final position and shape of snakes closely resemble actual jiber boundaries.bres touch, they form clumps. One can also observe that the gray level values inside individual fibres, especially the light ones (Fig. l), vary significantly. In some cases muscle fibres are not closely grouped together but are separated by thick connective tissue (Fig. 2). Due to inhomogenety of a specimen thickness and/or the optics of the microscope and the camera some parts of an image appear brighter than others. This is the case in Fig. 2, where the intensity changes form the top of the image to the bottom. Although in most cases fibres resemble convex polygons in each sample fibres with concavities can be found. The size of fibres in a sample may also vary significantly. In Fig. 1 the fibres are approximately of the same size, whereas the shape and size of fibres in Fig. 2 vary considerably.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.